Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Jobs are long-running tasks that are executed asynchronously. Jobs are identified by their job ID, in the form of job-1569583053767, which is returned when starting a job. Subsequent job updates are published over the websockets API.
There are two events that are published regarding jobs:
job-data-{jobId} - status update on the job, e.g. progress when training a neural network. Provides a single argument: { data: 'string with status' }.
job-finished-{jobId} - indicator that the job finished. Provides a single argument: { success: true } which indicates whether the job was executed successfully.
You can also cancel a job through the websocket by sending a job-cancel event. Pass in one parameter (the job ID).
Download the logs for a job (as a text file).
Project ID
Job ID
Maximum number of results
Log level (error, warn, info, debug)
OK
Generate features for the data explorer
Project ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Run an AI Actions job over a subset of data. This will instruct the block to apply the changes directly to your dataset. To preview, use "createPreviewAIActionsJob". To set the config use updateAIAction.
Project ID
AI Action ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Add keywords and noise data to a project (for getting started guide)
Project ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Retrains the current impulse with the last known parameters. Updates are streamed over the websocket API.
Project ID
Impulse ID. If this is unset then the default impulse is used.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Get the status for the multi-impulse migration job in this project. This is a separate route so public projects can access it. If no multi-impulse migration jobs are present, an error will be thrown.
Project ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job id, use this to refer back to the job. The web socket API also uses this ID.
External job identifier, this can be used to categorize jobs, and recover job status. E.g. set this to 'keras-192' for a Keras learning block with ID 192. When a user refreshes the page you can check whether a job is active for this ID and re-attach.
When the job was created.
When the job was started.
When the job was finished.
Whether the job finished successfully.
The IDs of users who should be notified when a job is finished.
Additional metadata associated with this job.
Job duration time in seconds from start to finished, measured by k8s job watcher.
Some job categories keep a counter on the job number, e.g. in synthetic data, so we know what the 1st, 2nd etc. job was in the UI.
Evaluates optimal model architecture
Project ID
Tuner coordinator job ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Export the training pipeline of a Keras block. Updates are streamed over the websocket API.
Project ID
Learn Block ID, use the impulse functions to retrieve the ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Cancel a running job.
Project ID
Job ID
If set to 'true', we won't wait for the job cluster to cancel the job, and will mark the job as finished.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Get all finished jobs for this project
Project ID
Start date
End date
Maximum number of results
Offset in results, can be used in conjunction with LimitResultsParameter to implement paging.
Whether to exclude jobs with a parent ID (so jobs started as part of another job)
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Active jobs
Job id, use this to refer back to the job. The web socket API also uses this ID.
External job identifier, this can be used to categorize jobs, and recover job status. E.g. set this to 'keras-192' for a Keras learning block with ID 192. When a user refreshes the page you can check whether a job is active for this ID and re-attach.
When the job was created.
When the job was started.
When the job was finished.
Whether the job finished successfully.
The IDs of users who should be notified when a job is finished.
Additional metadata associated with this job.
Job duration time in seconds from start to finished, measured by k8s job watcher.
Some job categories keep a counter on the job number, e.g. in synthetic data, so we know what the 1st, 2nd etc. job was in the UI.
Sets EON tuner primary model
Project ID
trial ID
Optional name. If no name is provided, the trial name is used.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Get all active jobs for this project
Project ID
Whether to exclude jobs with a parent ID (so jobs started as part of another job)
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Active jobs
Job id, use this to refer back to the job. The web socket API also uses this ID.
External job identifier, this can be used to categorize jobs, and recover job status. E.g. set this to 'keras-192' for a Keras learning block with ID 192. When a user refreshes the page you can check whether a job is active for this ID and re-attach.
When the job was created.
When the job was started.
When the job was finished.
Whether the job finished successfully.
The IDs of users who should be notified when a job is finished.
Additional metadata associated with this job.
Job duration time in seconds from start to finished, measured by k8s job watcher.
Some job categories keep a counter on the job number, e.g. in synthetic data, so we know what the 1st, 2nd etc. job was in the UI.
Update a job.
Project ID
Job ID
The IDs of users who should be notified when a job is finished.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Autotune DSP block parameters. Updates are streamed over the websocket API.
Project ID
DSP block ID to autotune parameters of
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Export all the data in the project in WAV format. Updates are streamed over the websocket API.
Project ID
Whether to retain crops and splits. If this is disabled, then the original files are returned (as they were uploaded).
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Restore a project to a certain public version. This can only applied to a project without data, and will overwrite your impulse and all settings.
Project ID
Source project ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
If an impulse migration previously failed, use this function to retry the job.
Project ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Get a summary of jobs, grouped by key. Used to report to users how much compute they've used.
Project ID
Start date
End date
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Length per category in milliseconds
Export all the data in the project as it was uploaded to Edge Impulse. Updates are streamed over the websocket API.
Project ID
Whether to rename the exported file names to an uploader friendly format (e.g. label.filename.cbor)
Whether to retain crops and splits. If this is disabled, then the original files are returned (as they were uploaded).
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Export the data of a Keras block (already split in train/validate data). Updates are streamed over the websocket API.
Project ID
Learn Block ID, use the impulse functions to retrieve the ID
Normalization that is applied to images. If this is not set then 0..1 is used. "0..1" gives you non-normalized pixels between 0 and 1. "-1..1" gives you non-normalized pixels between -1 and 1. "0..255" gives you non-normalized pixels between 0 and 255. "-128..127" gives you non-normalized pixels between -128 and 127. "torch" first scales pixels between 0 and 1, then applies normalization using the ImageNet dataset (same as torchvision.transforms.Normalize()). "bgr-subtract-imagenet-mean" scales to 0..255, reorders pixels to BGR, and subtracts the ImageNet mean from each channel.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Takes in a TFLite model and returns the latency, RAM and ROM used for this model. Updates are streamed over the websocket API (or can be retrieved through the /stdout endpoint). Use getProfileTfliteJobResult to get the results when the job is completed.
Project ID
A base64 encoded TFLite file
MCU used for calculating latency, query latencyDevices in listProject for a list of supported devices (and use the "mcu" property here).
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Generate new synthetic data
Project ID
The ID of a Synthetic Data transform block ID (public or private)
Properties for this synthetic data block
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Classifies all items in the testing dataset against the current impulse. Updates are streamed over the websocket API.
Project ID
Impulse ID. If this is unset then the default impulse is used.
Set of model variants to run the classify job against.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Take the raw training set and generate features from them. Updates are streamed over the websocket API.
Project ID
DSP block ID to generate features for
Whether to generate feature importance (only when available)
If set, skips feature explorer (used in tests)
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Restore a project to a certain version. This can only applied to a project without data, and will overwrite your impulse and all settings.
Project ID
Source project ID
Source project API key
Source project version ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Create a new version of the project. This stores all data and configuration offsite. If you have access to the enterprise version of Edge Impulse you can store your data in your own storage buckets (only through JWT token authentication).
Project ID
Data bucket ID. Keep empty to store in Edge Impulse hosted storage.
Whether to make this version available on a public URL.
Whether to run model testing when creating this version (if this value is omitted, it will use the current state of 'runModelTestingWhileVersioning' that is returned in ListVersionsResponse).
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Get the logs for the multi-impulse migration job in this project. This is a separate route so public projects can access it. If no multi-impulse migration jobs are present, an error will be thrown.
Project ID
Maximum number of results
Log level (error, warn, info, debug)
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Total number of logs (only the last 1000 lines are returned)
Get the logs for a job.
Project ID
Job ID
Maximum number of results
Log level (error, warn, info, debug)
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Total number of logs (only the last 1000 lines are returned)
Simulates real world usage and returns performance metrics.
Project ID
Impulse ID. If this is unset then the default impulse is used.
The label used to signify background noise in the impulse
Any other labels that should be considered equivalent to background noise
The key of an uploaded sample. If not present, a synthetic sample will be created.
The length of sample to create (required for synthetic samples)
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Generate code to run the impulse on an embedded device. When this step is complete use downloadBuild to download the artefacts. Updates are streamed over the websocket API.
Project ID
The name of the built target. You can find this by listing all deployment targets through listDeploymentTargetsForProject (via GET /v1/api/{projectId}/deployment/targets) and see the format type.
Impulse ID. If this is unset then the default impulse is used.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Generate code to run the impulse on an embedded device using an organizational deployment block. When this step is complete use downloadBuild to download the artefacts. Updates are streamed over the websocket API.
Project ID
Impulse ID. If this is unset then the default impulse is used.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Take the output from a DSP block and train an anomaly detection model using K-means or GMM. Updates are streamed over the websocket API.
Project ID
Learn Block ID, use the impulse functions to retrieve the ID
Which axes (indexes from DSP script) to include in the training set
Number of clusters for K-means, or number of components for GMM
32Minimum confidence rating required before tagging as anomaly
0.3If set, skips creating embeddings and measuring memory (used in tests)
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Do a dry-run of an AI Actions job over a subset of data. This will instruct the block to propose changes to data items (via "setSampleProposedChanges") rather than apply the changes directly.
Project ID
AI Action ID
The selected transformation block ID.
Parameters for the transformation block. These map back to the parameters in OrganizationTransformationBlock 'parameters' property.
If enabled, will load cached results from the previous preview job for unchanged jobs. Disable this if you're developing your own custom AI Labeling job, and want to always re-run all steps.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Begins post processing job
Project ID
Impulse ID. If this is unset then the default impulse is used.
Which dataset to use
Which algorithm container to use
Which evaluation container to use
The population size for the genetic algorithm
The maximum number of generations for the genetic algorithm
The tolerance for the design space
The tolerance for the objective space
The number of generations the termination criteria are averaged across
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Get the status for a job.
Project ID
Job ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job id, use this to refer back to the job. The web socket API also uses this ID.
External job identifier, this can be used to categorize jobs, and recover job status. E.g. set this to 'keras-192' for a Keras learning block with ID 192. When a user refreshes the page you can check whether a job is active for this ID and re-attach.
When the job was created.
When the job was started.
When the job was finished.
Whether the job finished successfully.
The IDs of users who should be notified when a job is finished.
Additional metadata associated with this job.
Job duration time in seconds from start to finished, measured by k8s job watcher.
Some job categories keep a counter on the job number, e.g. in synthetic data, so we know what the 1st, 2nd etc. job was in the UI.
Get all jobs for this project
Project ID
Start date
End date
Maximum number of results
Offset in results, can be used in conjunction with LimitResultsParameter to implement paging.
Whether to exclude jobs with a parent ID (so jobs started as part of another job)
Job key to filter on
Job category to filter on
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Active jobs
Job id, use this to refer back to the job. The web socket API also uses this ID.
External job identifier, this can be used to categorize jobs, and recover job status. E.g. set this to 'keras-192' for a Keras learning block with ID 192. When a user refreshes the page you can check whether a job is active for this ID and re-attach.
When the job was created.
When the job was started.
When the job was finished.
Whether the job finished successfully.
The IDs of users who should be notified when a job is finished.
Additional metadata associated with this job.
Job duration time in seconds from start to finished, measured by k8s job watcher.
Some job categories keep a counter on the job number, e.g. in synthetic data, so we know what the 1st, 2nd etc. job was in the UI.
Take the output from a DSP block and train a neural network using Keras. Updates are streamed over the websocket API.
Project ID
Learn Block ID, use the impulse functions to retrieve the ID
Whether to use visual or expert mode.
Minimum confidence score, if the neural network scores a sample below this threshold it will be flagged as uncertain.
Raw Keras script (only used in expert mode)
The visual layers for the neural network (only in visual mode).
Number of neurons or filters in this layer (only for dense, conv1d, conv2d) or in the final conv2d layer (only for transfer layers)
Kernel size for the convolutional layers (only for conv1d, conv2d)
Fraction of input units to drop (only for dropout) or in the final layer dropout (only for transfer layers)
Number of columns for the reshape operation (only for reshape)
Number of convolutional layers before the pooling layer (only for conv1d, conv2d)
Custom transfer learning model ID (when type is set to transfer_organization)
Number of training cycles (only in visual mode).
Learning rate (between 0 and 1) (only in visual mode).
Batch size used during training (only in visual mode).
Train/test split (between 0 and 1)
Whether to automatically balance class weights, use this for skewed datasets.
Use learned optimizer and ignore learning rate.
The data augmentation policy to use with image input
True if spectrogram augmentation is enabled. Other properties will be ignored if this is false.
True if warping along the time axis is enabled.
The amount of frequency masking to apply.
The amount of time masking to apply.
The amount of Gaussian noise to add.
Whether to profile the i8 model (might take a very long time)
If set, skips creating embeddings and measuring memory (used in tests)
True if Akida Edge Learning model creation is enabled. Other properties will be ignored if this is false.
Number of additional classes that will be added to the Edge Learning model.
Number of neurons in each class on the last layer in the Edge Learning model.
If the 'custom validation split' experiment is enabled, this metadata key is used to prevent group data leakage between train and validation datasets.
Whether the 'Advanced training settings' UI element should be expanded.
Whether the 'Augmentation training settings' UI element should be expanded.
Training parameters, this list depends on the list of parameters that the model exposes.
Capacity level for visual anomaly detection. Determines which set of default configurations to use. The higher capacity, the higher number of (Gaussian) components, and the more adapted the model becomes to the original distribution
Training parameters specific to the type of the learn block. Parameters may be adjusted depending on the model defined in the visual layers. Used for our built-in blocks.
The backbone to use for feature extraction
The number of layers in the feature extractor (1-3)
The pool size for the feature extractor
The sampling ratio for the coreset, used for anomaly scoring
The number of nearest neighbors to consider, used for anomaly scoring
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Get the results from a job started from startProfileTfliteJob (via a GET request).
Project ID
Job ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Estimated amount of RAM required by the model, measured in bytes
Estimated amount of ROM required by the model, measured in bytes
Estimated arena size required for model inference, measured in bytes
Estimated amount of RAM required by the model, measured in bytes
Estimated amount of ROM required by the model, measured in bytes
Estimated arena size required for model inference, measured in bytes
Estimated amount of RAM required by the model, measured in bytes
Estimated amount of ROM required by the model, measured in bytes
Estimated arena size required for model inference, measured in bytes
Make a version of a project public. This makes all data and state available (read-only) on a public URL, and allows users to clone this project.
Project ID
Version ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Evaluates every variant of the current impulse. Updates are streamed over the websocket API.
Project ID
Impulse ID. If this is unset then the default impulse is used.
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112Get the results from a job started from startProfileTfliteJob (via a POST request).
Project ID
Job ID
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Estimated amount of RAM required by the model, measured in bytes
Estimated amount of ROM required by the model, measured in bytes
Estimated arena size required for model inference, measured in bytes
Estimated amount of RAM required by the model, measured in bytes
Estimated amount of ROM required by the model, measured in bytes
Estimated arena size required for model inference, measured in bytes
Estimated amount of RAM required by the model, measured in bytes
Estimated amount of ROM required by the model, measured in bytes
Estimated arena size required for model inference, measured in bytes
Takes in a TFLite file and builds the model and SDK. Updates are streamed over the websocket API (or can be retrieved through the /stdout endpoint). Use getProfileTfliteJobResult to get the results when the job is completed.
Project ID
Impulse ID. If this is unset then the default impulse is used.
A base64 encoded pretrained model
The name of the built target. You can find this by listing all deployment targets through listDeploymentTargetsForProject (via GET /v1/api/{projectId}/deployment/targets) and see the format type.
A base64 encoded .npy file containing the features from your validation set (optional for onnx and saved_model) - used to quantize your model.
Optional, use a specific converter (only for ONNX models).
OK
Whether the operation succeeded
Optional error description (set if 'success' was false)
Job identifier. Status updates will include this identifier.
12873488112